Minimizing Sequential Confusion Error in Speech Command Recognition

TL;DR

This paper introduces a novel training criterion called MSCE for speech command recognition that significantly reduces command confusion errors on resource-constrained devices by using discriminative training and prior knowledge strategies.

Contribution

It proposes the MSCE training method with strategies for confusing set construction, improving discrimination among similar-sounding commands in SCR.

Findings

Reduced false reject rate by 33.7% at 0.01 FAR

Decreased confusion errors by 18.28%

Effective in resource-constrained edge devices

Abstract

Speech command recognition (SCR) has been commonly used on resource constrained devices to achieve hands-free user experience. However, in real applications, confusion among commands with similar pronunciations often happens due to the limited capacity of small models deployed on edge devices, which drastically affects the user experience. In this paper, inspired by the advances of discriminative training in speech recognition, we propose a novel minimize sequential confusion error (MSCE) training criterion particularly for SCR, aiming to alleviate the command confusion problem. Specifically, we aim to improve the ability of discriminating the target command from other commands on the basis of MCE discriminative criteria. We define the likelihood of different commands through connectionist temporal classification (CTC). During training, we propose several strategies to use prior knowledge creating a confusing sequence set for similar-sounding command instead of creating the whole non-target command set, which can better save the training resources and effectively reduce command confusion errors. Specifically, we design and compare three different strategies for confusing set construction. By using our proposed method, we can relatively reduce the False Reject Rate~(FRR) by 33.7% at 0.01 False Alarm Rate~(FAR) and confusion errors by 18.28% on our collected speech command set.